Tessl • The management layer for AI agent skills

The body is a strong, actionable single-file guide with executable commands, an explicit connection state machine, and good error-recovery guidance. Its main issues are a modest amount of marketing/boilerplate padding, an empty Description column wasting tokens in the actions table, and broken internal step references ('Step 2', '1b') that hurt navigation coherence.

Suggestions

Remove the empty Description column in the Popular actions table (or fill it with one-line parameter hints) and cut the marketing intro paragraph to save tokens.

Fix the dangling references: replace 'skip to Step 2' with a real anchor/heading and renumber '1b. Wait for the connection to be ready' into an explicit step sequence.

Dimension	Reasoning	Score
Conciseness	The body is dominated by useful commands and tables, but contains several trimmable passages: the marketing intro 'It's designed for businesses and individuals who want to streamline their communication across multiple channels', 'so you can focus on the integration logic rather than auth plumbing', and a 16-row Popular actions table whose Description column is entirely empty. This matches 'Mostly efficient but includes some unnecessary explanation or could be tightened' rather than score 4's 'minor instances'.	3 / 5
Actionability	Nearly all guidance is copy-paste ready: 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://1msg.io/" --json', 'membrane action run <actionId> --input '{"key": "value"}' --json', and a full proxy flag table. Minor gaps (placeholder CONNECTION_ID/QUERY args, no parameter examples in the actions table) keep it at 'mostly executable' rather than fully covering common cases.	4 / 5
Workflow Clarity	The connect-wait-act sequence has explicit checkpoints and feedback loops: poll until state is no longer BUILDING, handle clientAction types with re-polling after user action, and check the error field on CONFIGURATION_ERROR/SETUP_FAILED. However, coherence breaks because 'skip to Step 2' references steps that do not exist and the '#### 1b.' heading has no matching '1a' or numbered steps — minor validation/coherence gaps matching anchor 4.	4 / 5
Progressive Disclosure	The body is well-sectioned with clear headers (Install, Authentication, Connecting, Searching, Running, Proxy, Best practices) and no bundle files exist, so inline content is the only option. It is not score 5 because at ~170 lines with a large actions table and proxy flag table, some content could be split into reference files, and the document exceeds the under-50-lines simple-skill exception.	4 / 5
	Total	15 / 20 Passed

Description

57%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description correctly uses third person, includes an explicit 'Use when...' clause, and is anchored to a distinctive brand name. Its main weakness is generic action wording ('manage data, records, and automate workflows') that could apply to almost any integration, plus a lack of natural trigger synonyms for messaging-related requests.

Suggestions

Replace the generic action list with 1msg-specific capabilities, e.g. 'Send and receive messages, manage templates and media, and monitor channel status across 1msg.'

Add natural trigger variations users would say, such as 'Use when the user mentions 1msg, messaging channels, or wants to send WhatsApp/1msg messages.'

Avoid the vague trailing phrase 'interact with 1msg data' in favor of a concrete trigger tied to messaging tasks.

Dimension	Reasoning	Score
Specificity	"Manage data, records, and automate workflows" names the 1msg domain but the actions are generic; no concrete capabilities like sending messages, managing templates, or reading channel statistics are listed. It matches the anchor 'Names the domain but actions are minimal or generic' rather than score 3, which requires 1-2 concrete actions.	2 / 5
Completeness	Both parts are explicit: what ("Manage data, records, and automate workflows") and when ("Use when the user wants to interact with 1msg data"). It is not score 5 because the 'what' is generic rather than concrete capability phrases, leaving the 'when' to carry the description.	4 / 5
Trigger Term Quality	The only natural keyword is "1msg" ("interact with 1msg data"), with no common variations or synonyms such as messaging, messages, WhatsApp, or channels. This fits 'Some relevant keywords but missing common variations or synonyms' rather than score 4, which expects good broader coverage.	3 / 5
Distinctiveness Conflict Risk	Triggers are tied to the distinct "1msg" brand name, giving it a clear niche, but it could still overlap with other messaging skills since no disambiguating terms like "unified messaging" are present. Mostly distinct with minor overlap risk, matching anchor 4 rather than 5.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/1msg/SKILL.md
Revision: f484c82

Reviewed: 16 days ago

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

1msg

Table of Contents

Is this your skill?